Added Azure Blob Storage File and Container Loader (#1890)

Added support for document loaders for Azure Blob Storage using a
connection string. Fixes #1805

---------

Co-authored-by: Mick Vleeshouwer <mick@imick.nl>
pull/2046/head
Eduard van Valkenburg 1 year ago committed by GitHub
parent 42d725223e
commit c1a9d83b34
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -0,0 +1,135 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "a634365e",
"metadata": {},
"source": [
"# Azure Blob Storage Container\n",
"\n",
"This covers how to load document objects from a container on Azure Blob Storage."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "2f0cd6a5",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import AzureBlobStorageContainerLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "49815096",
"metadata": {},
"outputs": [],
"source": [
"#!pip install azure-storage-blob"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "321cc7f1",
"metadata": {},
"outputs": [],
"source": [
"loader = AzureBlobStorageContainerLoader(conn_str=\"<conn_str>\", container=\"<container>\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "2b11d155",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpaa9xl6ch/fake.docx'}, lookup_index=0)]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"loader.load()"
]
},
{
"cell_type": "markdown",
"id": "0690c40a",
"metadata": {},
"source": [
"## Specifying a prefix\n",
"You can also specify a prefix for more finegrained control over what files to load."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "72d44781",
"metadata": {},
"outputs": [],
"source": [
"loader = AzureBlobStorageContainerLoader(conn_str=\"<conn_str>\", container=\"<container>\", prefix=\"<prefix>\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "2d3c32db",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpujbkzf_l/fake.docx'}, lookup_index=0)]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"loader.load()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "885dc280",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

@ -0,0 +1,95 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "66a7777e",
"metadata": {},
"source": [
"# Azure Blob Storage File\n",
"\n",
"This covers how to load document objects from a Azure Blob Storage file."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9ec8a3b3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import AzureBlobStorageFileLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "43128d8d",
"metadata": {},
"outputs": [],
"source": [
"#!pip install azure-storage-blob"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "35d6809a",
"metadata": {},
"outputs": [],
"source": [
"loader = AzureBlobStorageFileLoader(conn_str='<connection string>', container='<container name>', blob_name='<blob name>')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "efd6be84",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpxvave6wl/fake.docx'}, lookup_index=0)]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"loader.load()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "93689594",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

@ -2,6 +2,12 @@
from langchain.document_loaders.airbyte_json import AirbyteJSONLoader
from langchain.document_loaders.azlyrics import AZLyricsLoader
from langchain.document_loaders.azure_blob_storage_container import (
AzureBlobStorageContainerLoader,
)
from langchain.document_loaders.azure_blob_storage_file import (
AzureBlobStorageFileLoader,
)
from langchain.document_loaders.blackboard import BlackboardLoader
from langchain.document_loaders.college_confidential import CollegeConfidentialLoader
from langchain.document_loaders.conllu import CoNLLULoader
@ -104,4 +110,6 @@ __all__ = [
"GoogleApiClient",
"CSVLoader",
"BlackboardLoader",
"AzureBlobStorageFileLoader",
"AzureBlobStorageContainerLoader",
]

@ -0,0 +1,40 @@
"""Loading logic for loading documents from an Azure Blob Storage container."""
from typing import List
from langchain.docstore.document import Document
from langchain.document_loaders.azure_blob_storage_file import (
AzureBlobStorageFileLoader,
)
from langchain.document_loaders.base import BaseLoader
class AzureBlobStorageContainerLoader(BaseLoader):
"""Loading logic for loading documents from Azure Blob Storage."""
def __init__(self, conn_str: str, container: str, prefix: str = ""):
"""Initialize with connection string, container and blob prefix."""
self.conn_str = conn_str
self.container = container
self.prefix = prefix
def load(self) -> List[Document]:
"""Load documents."""
try:
from azure.storage.blob import ContainerClient
except ImportError as exc:
raise ValueError(
"Could not import azure storage blob python package. "
"Please it install it with `pip install azure-storage-blob`."
) from exc
container = ContainerClient.from_connection_string(
conn_str=self.conn_str, container_name=self.container
)
docs = []
blob_list = container.list_blobs(name_starts_with=self.prefix)
for blob in blob_list:
loader = AzureBlobStorageFileLoader(
self.conn_str, self.container, blob.name # type: ignore
)
docs.extend(loader.load())
return docs

@ -0,0 +1,41 @@
"""Loading logic for loading documents from an Azure Blob Storage file."""
import os
import tempfile
from typing import List
from langchain.docstore.document import Document
from langchain.document_loaders.base import BaseLoader
from langchain.document_loaders.unstructured import UnstructuredFileLoader
class AzureBlobStorageFileLoader(BaseLoader):
"""Loading logic for loading documents from Azure Blob Storage."""
def __init__(self, conn_str: str, container: str, blob_name: str):
"""Initialize with connection string, container and blob name."""
self.conn_str = conn_str
self.container = container
self.blob = blob_name
def load(self) -> List[Document]:
"""Load documents."""
try:
from azure.storage.blob import BlobClient
except ImportError as exc:
raise ValueError(
"Could not import azure storage blob python package. "
"Please it install it with `pip install azure-storage-blob`."
) from exc
client = BlobClient.from_connection_string(
conn_str=self.conn_str, container_name=self.container, blob_name=self.blob
)
with tempfile.TemporaryDirectory() as temp_dir:
file_path = f"{temp_dir}/{self.container}/{self.blob}"
os.makedirs(os.path.dirname(file_path), exist_ok=True)
with open(f"{file_path}", "wb") as file:
blob_data = client.download_blob()
blob_data.readinto(file)
loader = UnstructuredFileLoader(file_path)
return loader.load()
Loading…
Cancel
Save